Thiago Alexandre Salgueiro Pardo
2026
Caracterização lexical e sintática de notícias falsas em português produzidas por humanos e por máquinas
Pedro Lucas Castro de Andrade | Renato Silva | Thiago Alexandre Salgueiro Pardo
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2
Pedro Lucas Castro de Andrade | Renato Silva | Thiago Alexandre Salgueiro Pardo
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2
Notícias falsas são um grande problema para a sociedade. Com a Inteligência Artificial generativa, notícias falsas produzidas pela máquina têm se proliferado, tornando o cenário mais desafiador. Apesar da relevância desse problema, em línguas sub-representadas como o Português, as pesquisas que buscam diferenciar notícias falsas de humanos e de máquinas são incipientes. Buscando preencher essa lacuna, este artigo explora os corpora Fake.br e FakeTrueBR expandidos com notícias falsas geradas automaticamente, caracterizando lexical e sintaticamente as notícias falsas produzidas por humanos e por máquina. Os resultados mostram que textos gerados por máquina apresentam palavras significativamente mais longas, maior uso de modificadores adjetivais e menor diversidade sintática, apesar de utilizarem mais regras sintáticas por sentença. Em contrapartida, textos humanos exibem maior variabilidade estilística em todas as dimensões analisadas.
Exploração de métodos simbólicos para detecção de emoções para o português
Stephanie Briere Americo | Thiago Alexandre Salgueiro Pardo
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2
Stephanie Briere Americo | Thiago Alexandre Salgueiro Pardo
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 2
Este trabalho investiga métodos simbólicos para a detecção de emoções em textos em português, considerando múltiplos córpus, domínios e diferentes configurações de pré-processamento. Os resultados mostram grande variação no desempenho absoluto entre domínios, mas estabilidade no desempenho relativo entre os métodos, evidenciando a influência das propriedades do córpus e o gradiente entre complexidade e interpretabilidade. A inclusão da classe neutra tende a degradar o desempenho ao aumentar a ambiguidade e, frequentemente, o desbalanceamento entre classes, enquanto um pré-processamento mais extensivo beneficia especialmente abordagens simbólicas. A análise qualitativa indica que parte dos erros decorre de ambiguidades linguísticas, do grande espaço para subjetividade no processo de anotação e das próprias nuances emocionais, reforçando a importância de avaliações comparativas multi-domínio.
Retrieval-Augmented Generation with Small Language Models for Fake News Detection
Lucca Baptista Silva Ferraz | Jhúlia de Souza Leal | Anderson Raymundo Avila | Thiago Alexandre Salgueiro Pardo | Fernando Batista | Renato Moraes Silva
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
Lucca Baptista Silva Ferraz | Jhúlia de Souza Leal | Anderson Raymundo Avila | Thiago Alexandre Salgueiro Pardo | Fernando Batista | Renato Moraes Silva
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
The spread of online misinformation has made fake news detection an essential tool for mitigating its negative impact, but many studies often disregard the temporal information, and existing datasets become outdated as news evolve. Some modern solutions using Retrieval-Augmented Generation (RAG) can solve the problem of unseen news events by providing context to the models. However, there are no studies evaluating the feasibility of web searches to attain context to decide whether a news article is true or not. This work aims to address this gap by conducting a comparative study between RAG-based solutions, traditional fake news classification methods, and deep learning-based methods. The results show that although RAG is a modern and promising technique, it cannot outperform techniques already adopted in the literature.
2025
The revision of linguistic annotation in the Universal Dependencies framework: a look at the annotators’ behavior
Magali Sanches Duran | Lucelene Lopes | Thiago Alexandre Salgueiro Pardo
Proceedings of the 19th Linguistic Annotation Workshop (LAW-XIX-2025)
Magali Sanches Duran | Lucelene Lopes | Thiago Alexandre Salgueiro Pardo
Proceedings of the 19th Linguistic Annotation Workshop (LAW-XIX-2025)
This paper presents strategies to revise an automatically annotated corpus according to the Universal Dependencies framework and discusses the learned lessons, mainly regarding the annotators’ behavior. The revision strategies are not relying on examples from any specific language and, because they are languageindependent, can be adopted in any language and corpus annotation initiative.
2024
Grammar Induction for Brazilian Indigenous Languages
Diego Pedro Gonçalves da Silva | Thiago Alexandre Salgueiro Pardo
Proceedings of the 16th International Conference on Computational Processing of Portuguese - Vol. 2
Diego Pedro Gonçalves da Silva | Thiago Alexandre Salgueiro Pardo
Proceedings of the 16th International Conference on Computational Processing of Portuguese - Vol. 2
Inferências baseadas em sintaxe: a anotação de sujeitos implícitos
Magali Sanches Duran | Maria das Graças Volpe Nunes | Thiago Alexandre Salgueiro Pardo
Proceedings of the 15th Brazilian Symposium in Information and Human Language Technology
Magali Sanches Duran | Maria das Graças Volpe Nunes | Thiago Alexandre Salgueiro Pardo
Proceedings of the 15th Brazilian Symposium in Information and Human Language Technology
Desambiguação de lema e atributos morfológicos na anotação do córpus Porttinari-base
Lucelene Lopes | Magali S. Duran | Thiago Alexandre Salgueiro Pardo
Proceedings of the 15th Brazilian Symposium in Information and Human Language Technology
Lucelene Lopes | Magali S. Duran | Thiago Alexandre Salgueiro Pardo
Proceedings of the 15th Brazilian Symposium in Information and Human Language Technology
Investigating Paraphrase Generation as a Data Augmentation Strategy for Low-Resource AMR-to-Text Generation
Marco Antonio Sobrevilla Cabezudo | Marcio Lima Inacio | Thiago Alexandre Salgueiro Pardo
Proceedings of the 17th International Natural Language Generation Conference
Marco Antonio Sobrevilla Cabezudo | Marcio Lima Inacio | Thiago Alexandre Salgueiro Pardo
Proceedings of the 17th International Natural Language Generation Conference
Abstract Meaning Representation (AMR) is a meaning representation (MR) designed to abstract away from syntax, allowing syntactically different sentences to share the same AMR graph. Unlike other MRs, existing AMR corpora typically link one AMR graph to a single reference. This paper investigates the value of paraphrase generation in low-resource AMR-to-Text generation by testing various paraphrase generation strategies and evaluating their impact. The findings show that paraphrase generation significantly outperforms the baseline and traditional data augmentation methods, even with fewer training instances. Human evaluations indicate that this strategy often produces syntactic-based paraphrases and can exceed the performance of previous approaches. Additionally, the paper releases a paraphrase-extended version of the AMR corpus.
Syntactic parsing: where are we going?
Lucelene Lopes | Thiago Alexandre Salgueiro Pardo | Magali Duran
Proceedings of the 15th Brazilian Symposium in Information and Human Language Technology
Lucelene Lopes | Thiago Alexandre Salgueiro Pardo | Magali Duran
Proceedings of the 15th Brazilian Symposium in Information and Human Language Technology
2023
Tipologia de fenômenos ortograficos e lexicais em CGU: o caso dos tweets do mercado financeiro
Clarissa Scandarolli | Ariani Di Felippo | Norton Roman | Thiago Alexandre Salgueiro Pardo
Proceedings of the 14th Brazilian Symposium in Information and Human Language Technology
Clarissa Scandarolli | Ariani Di Felippo | Norton Roman | Thiago Alexandre Salgueiro Pardo
Proceedings of the 14th Brazilian Symposium in Information and Human Language Technology
Etiquetagem morfossintatica multigênero para o português do Brasil segundo o modelo Universal Dependencies
Emanuel Huber Silva | Thiago Alexandre Salgueiro Pardo | Norton Trevisan Roman
Proceedings of the 14th Brazilian Symposium in Information and Human Language Technology
Emanuel Huber Silva | Thiago Alexandre Salgueiro Pardo | Norton Trevisan Roman
Proceedings of the 14th Brazilian Symposium in Information and Human Language Technology
Enhanced dependencies para o português brasileiro
Adriana S. Pagano | Magali Sanches Duran | Thiago Alexandre Salgueiro Pardo
Proceedings of the 2nd Edition of the Universal Dependencies Brazilian Festival
Adriana S. Pagano | Magali Sanches Duran | Thiago Alexandre Salgueiro Pardo
Proceedings of the 2nd Edition of the Universal Dependencies Brazilian Festival
Proceedings of the 2nd Edition of the Universal Dependencies Brazilian Festival
Thiago Alexandre Salgueiro Pardo | Magali Sanches Duran | Lucelene Lopes
Proceedings of the 2nd Edition of the Universal Dependencies Brazilian Festival
Thiago Alexandre Salgueiro Pardo | Magali Sanches Duran | Lucelene Lopes
Proceedings of the 2nd Edition of the Universal Dependencies Brazilian Festival
A Sentiment Analysis Benchmark for Automated Machine Learning Applications and a Proof of Concept in Hate Speech Detection
Marilia Silva | Vitor de Oliveira | Thiago Alexandre Salgueiro Pardo
Proceedings of the 14th Brazilian Symposium in Information and Human Language Technology
Marilia Silva | Vitor de Oliveira | Thiago Alexandre Salgueiro Pardo
Proceedings of the 14th Brazilian Symposium in Information and Human Language Technology
Verifica-UD: a Verifier for Universal Dependencies Annotation for Portuguese
Lucelene Lopes | Magali Sanches Duran | Thiago Alexandre Salgueiro Pardo
Proceedings of the 2nd Edition of the Universal Dependencies Brazilian Festival
Lucelene Lopes | Magali Sanches Duran | Thiago Alexandre Salgueiro Pardo
Proceedings of the 2nd Edition of the Universal Dependencies Brazilian Festival
Induão Gramatical para o Português: a Contribuião da Informação Mutua para Descoberta de Relaões de Dependência
Diego da Silva | Thiago Alexandre Salgueiro Pardo
Proceedings of the 14th Brazilian Symposium in Information and Human Language Technology
Diego da Silva | Thiago Alexandre Salgueiro Pardo
Proceedings of the 14th Brazilian Symposium in Information and Human Language Technology
2022
Evaluating Methods for Extraction of Aspect Terms in Opinion Texts in Portuguese - the Challenges of Implicit Aspects
Mateus Machado | Thiago Alexandre Salgueiro Pardo
Proceedings of the Thirteenth Language Resources and Evaluation Conference
Mateus Machado | Thiago Alexandre Salgueiro Pardo
Proceedings of the Thirteenth Language Resources and Evaluation Conference
One of the challenges of aspect-based sentiment analysis is the implicit mention of aspects. These are more difficult to identify and may require world knowledge to do so. In this work, we evaluate frequency-based, hybrid, and machine learning methods, including the use of the pre-trained BERT language model, in the task of extracting aspect terms in opinionated texts in Portuguese, emphasizing the analysis of implicit aspects. Besides the comparative evaluation of methods, the differential of this work lies in the analysis’s novelty using a typology of implicit aspects that shows the knowledge needed to identify each implicit aspect term, thus allowing a mapping of the strengths and weaknesses of each method.
UDConcord: A Concordancer for Universal Dependencies Treebanks
Lucas Gabriel Mendes Miranda | Thiago Alexandre Salgueiro Pardo
Proceedings of the Universal Dependencies Brazilian Festival
Lucas Gabriel Mendes Miranda | Thiago Alexandre Salgueiro Pardo
Proceedings of the Universal Dependencies Brazilian Festival
Proceedings of the Universal Dependencies Brazilian Festival
Thiago Alexandre Salgueiro Pardo | Ariani Di-Felippo | Norton Trevisan Roman
Proceedings of the Universal Dependencies Brazilian Festival
Thiago Alexandre Salgueiro Pardo | Ariani Di-Felippo | Norton Trevisan Roman
Proceedings of the Universal Dependencies Brazilian Festival
2015
Semi-Supervised Never-Ending Learning in Rhetorical Relation Identification
Erick Galani Maziero | Graeme Hirst | Thiago Alexandre Salgueiro Pardo
Proceedings of the International Conference Recent Advances in Natural Language Processing
Erick Galani Maziero | Graeme Hirst | Thiago Alexandre Salgueiro Pardo
Proceedings of the International Conference Recent Advances in Natural Language Processing
2013
An Evaluation of the Brazilian Portuguese LIWC Dictionary for Sentiment Analysis
Pedro P. Balage Filho | Thiago Alexandre Salgueiro Pardo | Sandra M. Aluísio
Proceedings of the 9th Brazilian Symposium in Information and Human Language Technology
Pedro P. Balage Filho | Thiago Alexandre Salgueiro Pardo | Sandra M. Aluísio
Proceedings of the 9th Brazilian Symposium in Information and Human Language Technology
Desambiguação Lexical de Sentido com uso de Informação Multidocumento por meio de Redes de Co-ocorrência (Word Sense Disambiguation with the Use of Multi-document Information with Cooccurrence Nets) [in Portuguese]
Fernando Antônio Asevedo Nóbrega | Thiago Alexandre Salgueiro Pardo
Proceedings of the 9th Brazilian Symposium in Information and Human Language Technology
Fernando Antônio Asevedo Nóbrega | Thiago Alexandre Salgueiro Pardo
Proceedings of the 9th Brazilian Symposium in Information and Human Language Technology
2011
Um Processo Baseado em Parágrafos para a Extração de Tratamentos em Artigos Científicos do Domínio Biomédico (A Paragraph-based Process to Extraction of Treatments from Biomedical Scientific Papers) [in Portuguese]
Juliana Lilian Duque | Pablo Freire Matos | Cristina Dutra de Aguiar Ciferri | Thiago Alexandre Salgueiro Pardo | Ricardo Rodrigues Ciferri
Proceedings of the 8th Brazilian Symposium in Information and Human Language Technology
Juliana Lilian Duque | Pablo Freire Matos | Cristina Dutra de Aguiar Ciferri | Thiago Alexandre Salgueiro Pardo | Ricardo Rodrigues Ciferri
Proceedings of the 8th Brazilian Symposium in Information and Human Language Technology
Search
Fix author
Co-authors
- Magali Sanches Duran 6
- Lucelene Lopes 5
- Ariani Di Felippo 2
- Erick Galani Maziero 2
- Norton Trevisan Roman 2
- Renato Moraes Silva 2
- Sandra Aluísio 1
- Stephanie Briere Americo 1
- Anderson Raymundo Avila 1
- Pedro Balage Filho 1
- Fernando Batista 1
- Maria Lucia Castro Jorge 1
- Ricardo Rodrigues Ciferri 1
- Juliana Lilian Duque 1
- Magali S. Duran 1
- Lucca Baptista Silva Ferraz 1
- Graeme Hirst 1
- Marcio Lima Inácio 1
- Jhúlia de Souza Leal 1
- Mateus Machado 1
- Pablo Freire Matos 1
- Lucas Gabriel Mendes Miranda 1
- Fernando Antônio Asevedo Nóbrega 1
- Vitor de Oliveira 1
- Adriana S. Pagano 1
- Norton Roman 1
- Clarissa Scandarolli 1
- Emanuel Huber Silva 1
- Marilia Silva 1
- Diego da Silva 1
- Marco Antonio Sobrevilla Cabezudo 1
- Maria das Graças Volpe Nunes 1
- Diego Pedro Gonçalves da Silva 1
- Cristina Dutra de Aguiar Ciferri 1
- Pedro Lucas Castro de Andrade 1